“ASR Status Report 2017-4-10”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
第37行： 第37行：
 
|Lantian Li   
 
|Lantian Li   
 
||  
 
||  
−
*
+
* Deep speaker : GMM-tnorm and frame-PLDA is effective.
 
||  
 
||  
−
*
+
* Deep speaker : phone-aware.
 
|-
 
|-
  

2017年5月5日 (五) 09:07的最后版本

Date People Last Week This Week
2017.4.10


Yanqing Wang
Ying Shi
  • joint system noise test speech task []
  • because of the downtime of work7 the result of speaker noise test is lost ....
  • write graduation thesis
Yixiang Chen
Lantian Li
  • Deep speaker : GMM-tnorm and frame-PLDA is effective.
  • Deep speaker : phone-aware.
Zhiyuan Tang
  • WSJ AM assists AP-OLR lid, noise, length results
  • continue noise robustness analysis and finish most important experiments



Date People Last Week This Week
2017.4.5


Yanqing Wang
  • read source code of thchs30 and run the shell scripts
  • continue on the DNN-HMM and source code of thchs30
Ying Shi
  • baseline of swbd speech recognition and partial collaborative training of new joint structure(enhance speech task) finished here
  • baseline of fisher SRE partial collaborative training of new joint structure(enhance speaker task)
Yixiang Chen
  • help for frame-PLDA
Lantian Li
  • Deep speaker : GMM-tnorm and frame-PLDA is effective.
  • LM adaptation for Accent ASR.
  • Deep speaker : phone-aware
Zhiyuan Tang
  • WSJ AM assists AP-OLR lid. results
  • noise robustness analysis, etc.
取自“http://index.cslt.org/mediawiki/index.php?title=ASR_Status_Report_2017-4-10&oldid=26865”